Evaluation method and equipment for feasibility grade of green mine development and medium

Abstract

The invention discloses a green mine development feasibility grade evaluation method and device and a medium, and relates to the technical field of green mine development, and the method comprises the steps: carrying out the preliminary definition and classification of evaluation indexes from four dimensions of resource saving, environment friendliness, ecological harmony and mine-land cooperation according to a mine development data set, and carrying out the calculation of the evaluation indexes; a multi-dimensional comprehensive evaluation system is constructed; all dimension indexes are obtained from a multi-dimension comprehensive evaluation system, a complex problem is structured in combination with an analytic hierarchy process, fuzziness and uncertainty in the evaluation process are processed in combination with a fuzzy comprehensive evaluation method, and a grading evaluation model is established; inputting each dimension index into a grading evaluation model for structured decomposition and fuzzy reasoning, outputting a mine development feasibility score, and dividing a preliminary development feasibility grade; the feasibility evaluation of mine development is more comprehensive and accurate, and each key factor is ensured to be effectively considered.

Description

Technical Field

[0001] This invention relates to the field of green mine development technology, and in particular to a method, equipment and medium for assessing the feasibility level of green mine development. Background Technology

[0002] In recent years, with the deepening global focus on green and sustainable development, the sustainable development of the mining industry has gradually become a key research focus for both academia and industry. Gold mining, in particular, faces significant challenges due to its limited resources, harsh mining environment, and potential impacts on ecosystems. How to achieve environmental protection, resource conservation, and social harmony while ensuring economic benefits has become a pressing challenge for the mining industry. Currently, the technical means for assessing the feasibility and environmental impact of gold mining have evolved from traditional single economic assessment methods to multi-dimensional comprehensive assessment methods. Therefore, in recent years, research based on Life Cycle Assessment (LCA) and multi-dimensional comprehensive assessment models has gained increasing attention, aiming to provide more comprehensive and scientific decision support for mining operations.

[0003] While existing assessment methods have promoted the green development of gold mining to some extent, they still have some shortcomings in data processing and comprehensive evaluation. Existing methods often rely on relatively simple indicator systems for mine development assessment, making it difficult to comprehensively consider the multiple impacts of mining on resources, the environment, ecology, and society. Furthermore, existing assessment systems have limitations in the accuracy and stability of assessment standards and data processing methods when facing complex and diverse mining environments, especially in handling data noise, ambiguity, and uncertainty; traditional evaluation methods struggle to provide sufficient support. Therefore, how to scientifically assess the feasibility of gold mining under multi-dimensional and complex conditions, especially how to fully consider ecological and social benefits in the assessment, has become an important issue in the current technological field. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method for assessing the feasibility level of green mine development, addressing the shortcomings in comprehensively considering multi-dimensional impacts and handling data noise.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for assessing the feasibility level of green mine development, which includes collecting multi-dimensional assessment data of mine development and obtaining a mine development dataset through data cleaning, denoising and standardization; Based on the mining development dataset, the evaluation indicators are preliminarily defined and classified from four dimensions: resource conservation, environmental friendliness, ecological harmony, and mine-land synergy, and a multi-dimensional comprehensive evaluation system is constructed. The multi-dimensional comprehensive evaluation system obtains indicators for each dimension, combines the analytic hierarchy process to structure complex problems, and combines the fuzzy comprehensive evaluation method to deal with the fuzziness and uncertainty in the evaluation process, and establishes a hierarchical evaluation model. The indicators of each dimension are input into the hierarchical evaluation model for structured decomposition and fuzzy reasoning, outputting the feasibility score of mine development and classifying the preliminary development feasibility level. Based on the feasibility score and preliminary feasibility level of mine development, the environmental, economic and social benefits of mine development activities are quantified using the full life cycle assessment method, and the comprehensive benefit quantification results are output. The comprehensive benefit quantification results are divided into multiple dimensions and levels to obtain the feasibility level of mine development.

[0007] As a preferred embodiment of the method for assessing the feasibility level of green mine development according to the present invention, the specific steps for obtaining the mine development dataset are as follows: The system examines multi-dimensional assessment data of mine development, identifies missing and outlier values, fills in missing values ​​and corrects outliers, and outputs a cleaned dataset. Identify abnormal fluctuations in the cleaned data, remove noise through smoothing and correct the abnormal fluctuations, and output the denoised dataset. Adjust the scale of the denoised dataset, compare all numerical data within the same range, process categorical data into numerical data, and output the mining development dataset.

[0008] As a preferred embodiment of the method for assessing the feasibility level of green mine development as described in this invention, the following steps are taken: based on a mine development dataset, preliminary definitions and classifications are made of assessment indicators from four dimensions: resource conservation, environmental friendliness, ecological harmony, and mine-land synergy, to construct a multi-dimensional comprehensive evaluation system. Statistical analysis and data mining are performed on mining data, environmental monitoring data, resource utilization data and social impact data in the mining development dataset. The analysis focuses on resource consumption, environmental impact, ecological restoration and social collaboration involved in the mining process. Four evaluation dimensions are defined and corresponding evaluation indicators are selected for each evaluation dimension. A multi-dimensional comprehensive evaluation framework is constructed based on four evaluation dimensions. The evaluation indicators of each evaluation dimension are standardized, and preliminary weights are assigned to each evaluation indicator to obtain standardized weighted evaluation indicators. In the multi-dimensional comprehensive evaluation framework, the evaluation indicators under each evaluation dimension are managed hierarchically, and a hierarchical indicator structure is output. By integrating hierarchical indicator structures, standardized weighted evaluation indicators, and preliminary weights, a multi-dimensional comprehensive evaluation system is constructed.

[0009] As a preferred embodiment of the feasibility assessment method for green mine development described in this invention, the steps include: obtaining indicators from various dimensions of a multi-dimensional comprehensive evaluation system, structuring complex problems using the analytic hierarchy process (AHP), and handling fuzzy and uncertainties in the assessment process using the fuzzy comprehensive evaluation method to establish a graded evaluation model. The specific steps are as follows: The evaluation indicators for each evaluation dimension are extracted from the multi-dimensional comprehensive evaluation system, and the evaluation indicators are numbered and classified according to the dimension, and a set of classified evaluation indicators is output. Based on the set of classification and evaluation indicators, the hierarchical analysis method is used to construct a hierarchical structured indicator system, with the set of classification and evaluation indicators as the top level, the evaluation dimensions as the second level, and the evaluation indicators as the third level. The weight values ​​of each evaluation dimension and evaluation indicator are automatically calculated based on the hierarchical structured indicator system. The specific numerical data of each evaluation indicator are converted into fuzzy linguistic variables, and the membership value of each evaluation indicator is calculated according to the membership function. By combining membership values ​​and weight values, fuzzy comprehensive evaluation results for each evaluation dimension are derived through fuzzy computation, thus obtaining a hierarchical evaluation model.

[0010] As a preferred embodiment of the feasibility assessment method for green mine development described in this invention, the specific steps of inputting various dimensional indicators into a hierarchical assessment model for structured decomposition and fuzzy reasoning, and outputting a mine development feasibility score, are as follows: The evaluation indicators and corresponding weight values ​​of each evaluation dimension are input into the hierarchical evaluation model. Each evaluation indicator is classified, sorted, and hierarchically decomposed to output dimensional structure data. Based on the dimensional structure data and the membership value of each evaluation indicator, a fuzzy inference algorithm is used to perform a fuzzy comprehensive evaluation of each evaluation dimension and calculate the comprehensive fuzzy score of each evaluation dimension. The feasibility score for mine development is calculated by weighting all the comprehensive fuzzy scores together with the dimensional weights.

[0011] As a preferred embodiment of the method for assessing the feasibility level of green mine development according to the present invention, the preliminary development feasibility level is determined by setting a feasibility score interval based on the distribution of mine development feasibility scores, comparing the mine development feasibility score with the feasibility score interval, and determining the interval to which the mine development feasibility score belongs.

[0012] As a preferred embodiment of the green mine development feasibility assessment method described in this invention, the step of quantifying the environmental, economic, and social benefits of mine development activities based on the mine development feasibility score and preliminary development feasibility level, and outputting a comprehensive benefit quantification result, is as follows: Based on the mine development feasibility score and preliminary development feasibility level, the life cycle stages of mine development are determined, and corresponding stage weight values ​​are assigned to each life cycle stage. Based on the various life cycle stages of mining development activities, define quantitative indicators for the environmental, economic, and social benefits of each life cycle stage, and obtain the corresponding benefit indicators. By combining the stage weights and benefit indicators of each life cycle stage, the environmental, economic, and social benefit scores for each life cycle stage are calculated; the environmental, economic, and social benefit scores of each life cycle stage are then integrated into a comprehensive quantitative result of the benefits of mine development.

[0013] As a preferred embodiment of the method for assessing the feasibility level of green mine development according to the present invention, the specific steps for obtaining the mine development feasibility level by dividing the comprehensive benefit quantification results into multiple dimensions and levels are as follows. Based on each comprehensive benefit quantification result, a multi-dimensional benefit classification standard is set, and a different benefit range is defined for each comprehensive benefit quantification result. The range is divided according to the multi-dimensional benefit classification standard to obtain multiple levels of results. Based on the hierarchical results of each benefit dimension, environmental benefits are defined as the primary dimension, economic benefits as the secondary dimension, and social benefits as the third priority dimension, and the priority order is obtained. The results from multiple levels are merged according to priority and hierarchical merging rules to obtain the feasibility level of mine development.

[0014] In a second aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the method for assessing the feasibility level of green mine development as described in the first aspect of the present invention.

[0015] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein, when the computer program is executed by a processor, it implements any step of the method for assessing the feasibility level of green mine development as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By defining and classifying relevant assessment indicators from four dimensions—resource conservation, environmental friendliness, ecological harmony, and mine-land synergy—a multi-dimensional comprehensive evaluation system is constructed to ensure that all aspects of the impact of mining development are fully considered, thus promoting green and sustainable development. Furthermore, by using the analytic hierarchy process (AHP) to structure assessment indicators and combining it with fuzzy comprehensive evaluation methods to handle uncertainties, the accuracy and adaptability of the assessment results are improved, providing strong support for scientific decision-making in mining development. Finally, the feasibility assessment of mining development is made more comprehensive and accurate, ensuring that all key factors are effectively considered. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart for the assessment method of feasibility level of green mine development.

[0019] Figure 2 A flowchart for data preprocessing.

[0020] Figure 3 A flowchart for constructing a multi-dimensional comprehensive evaluation system.

[0021] Figure 4 A flowchart for establishing a tiered assessment model. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0025] Reference Figures 1-4As one embodiment of the present invention, this embodiment provides a method for assessing the feasibility level of green mine development, comprising the following steps: S1. Collect multi-dimensional assessment data of mine development. Through data cleaning, noise reduction and standardization, obtain the mine development dataset.

[0026] It should be noted that the multi-dimensional assessment data for mine development includes mining data, environmental monitoring data, resource utilization data, and social impact data. Specifically: mining data comes from the daily production records of mining enterprises, including ore production, mining depth, and equipment operation logs; environmental monitoring data comes from real-time monitoring values ​​uploaded by air quality monitoring stations, automatic water quality monitoring instruments, and noise sensors deployed in and around the mining area, as well as soil and water testing reports issued periodically by third-party environmental testing agencies; resource utilization data comes from the material balance ledgers, water resource meters, and energy consumption statistics reports of ore dressing plants and tailings ponds; and social impact data comes from employment and population data released by local government statistical departments, community questionnaire survey results, and publicly disclosed documents regarding corporate social responsibility.

[0027] S1.1. Examine the multi-dimensional assessment data of mine development, identify missing values ​​and outliers, fill in the missing values ​​and correct the outliers, and output the cleaned dataset.

[0028] Furthermore, the process iterates through every record in the multi-dimensional assessment data of mine development, identifying the location of missing values ​​and outliers in numerical fields (e.g., judging values ​​that exceed the reasonable range using the 3σ principle or interquartile range method); then, missing values ​​are filled using mean imputation or K-nearest neighbor imputation based on similar samples, and outliers are corrected or replaced based on contextual logic or adjacent time point data. All processed records are then integrated to output the cleaned dataset.

[0029] S1.2 Identify abnormal fluctuations in the cleaned data, remove noise through smoothing and correct the abnormal fluctuations, and output the denoised dataset.

[0030] Furthermore, for numerical fields with time-series characteristics in the cleaned dataset, the rate of change or local standard deviation of adjacent points is calculated, and abrupt changes exceeding the local fluctuation tolerance threshold are marked as abnormal fluctuations. Subsequently, the cleaned dataset is smoothed using the sliding window averaging method or Savitzky-Golay filter, replacing the abnormal fluctuation parts with smooth curve fitting values, integrating all corrected records, and outputting the denoised dataset.

[0031] It should be noted that the local fluctuation tolerance threshold is based on the historical observation sequence of the same indicator in the cleaned dataset, and the interquartile range (IQR) of the absolute value of the first difference is calculated. The lower bound of the local fluctuation tolerance threshold is set as the difference between the first quartile (Q1) and 1.5 times the IQR, and the upper bound is set as the sum of the third quartile (Q3) and 1.5 times the IQR. The range of values ​​for the local fluctuation tolerance threshold is determined based on the actual fluctuation amplitude of similar indicators in the stable operation phase of the multi-dimensional assessment data of mine development. For example, the value is 0.2 to 0.5.

[0032] S1.3 Adjust the scale of the denoised dataset, compare all numerical data within the same range, process categorical data into numerical data, and output the mining development dataset.

[0033] Furthermore, the min-max normalization method is applied to all numerical fields in the denoised dataset to linearly map the values ​​of each field to the interval between 0 and 1, making numerical data of different dimensions comparable. Then, for the categorical data fields in the denoised dataset, if they are ordered categories (such as "low, medium and high"), they are encoded into integers in order of rank (from low to high). If they are unordered categories (such as "mine area A and mine area B"), they are converted into multiple binary numerical fields using one-hot encoding. All processed fields are merged to output the mining development dataset.

[0034] S2. Based on the mining development dataset, the evaluation indicators are initially defined and classified from four dimensions: resource conservation, environmental friendliness, ecological harmony, and mine-land synergy, and a multi-dimensional comprehensive evaluation system is constructed.

[0035] S2.1 Statistical analysis and data mining are performed on the mining data, environmental monitoring data, resource utilization data and social impact data in the mining development dataset. The analysis focuses on resource consumption, environmental impact, ecological restoration and social collaboration involved in the mining process. Four evaluation dimensions are defined and corresponding evaluation indicators are selected for each evaluation dimension.

[0036] Furthermore, the study calculates the time-related trends and fluctuation ranges of fields such as ore recovery rate and energy consumption per unit product in mining data; it statistically analyzes the distribution frequency and extreme values ​​of fields such as wastewater discharge compliance rate and dust emission concentration in environmental monitoring data at different monitoring points; it analyzes the stability and concentration range of the numerical sequences of fields such as tailings comprehensive utilization rate and water resource recycling rate in resource utilization data; and it statistically analyzes the differences in values ​​of fields such as local employment ratio and community infrastructure sharing rate in social impact data across different mining area samples. Subsequently, using principal component analysis, the statistical results of the above fields are used as input variables to extract principal components with high cumulative variance contribution rates. Based on the correspondence between variables and principal components in the principal component loading matrix, high-loading variables are categorized into the same theme, thereby defining four evaluation dimensions: resource conservation, environmental friendliness, ecological harmony, and mine-land synergy. Finally, the study extracts the key variables that best represent the characteristics of each dimension from the high-loading indicator group, forming a set of representative evaluation indicators for each dimension.

[0037] S2.2. Construct a multi-dimensional comprehensive evaluation framework based on four evaluation dimensions, standardize the evaluation indicators of each evaluation dimension, and assign preliminary weights to each evaluation indicator to obtain standardized weighted evaluation indicators.

[0038] Furthermore, the evaluation indicators under each evaluation dimension are standardized according to their numerical characteristics. For positive indicators (such as ore recovery rate and vegetation restoration area ratio), the minimum-maximum standardization formula is used to map them to the interval between 0 and 1. For negative indicators (such as dust emission concentration and unit product energy consumption), polarity is first reversed and then minimum-maximum standardization is performed. Subsequently, the entropy weight method is used to calculate the information entropy of each evaluation indicator, and the initial weight of each evaluation indicator is determined in reverse according to the magnitude of the information entropy. The smaller the information entropy, the greater the difference between samples and the more effective information contained in the evaluation indicator, and the higher its initial weight. The standardized value of each evaluation indicator is multiplied by its corresponding initial weight to obtain the standardized weighted evaluation indicator. The information entropy of each evaluation indicator is calculated using the entropy weight method, and the expression is as follows: ; In the formula, No. The information entropy of an evaluation indicator is used to measure the dispersion of the value of the evaluation indicator across all samples. The smaller the value, the more effective information the evaluation indicator provides. It is the total number of samples. The natural logarithm of is used as a normalization coefficient to ensure that the value of information entropy is constrained to be between 0 and 1. It is the first The sample at the th The normalized weight of each evaluation indicator is calculated from the standardized value of that evaluation indicator in all samples. It is the total number of samples in the mining development dataset, that is, the number of mining instances participating in the evaluation, and is dimensionless; It is the sample sequence number, and its value range is... This is used to iterate through all samples; It is the evaluation indicator number, used to identify the specific evaluation indicators under the four evaluation dimensions of resource conservation, environmental friendliness, ecological harmony and mining-land synergy; Normalized weight The natural logarithm, in The value is set to 0 by convention to ensure the continuity and computability of the mathematical expression; It should be noted that numerical characteristics refer to the original directional (positive or negative) values ​​of the evaluation indicators in the mining development dataset, which are obtained by judging the trend of the impact of increasing indicator values ​​on the feasibility of mining development.

[0039] Entropy weighting is an objective weighting method based on the theory of information entropy. It determines the weight of each evaluation indicator in a mining development dataset by calculating the degree of dispersion of its values ​​across samples.

[0040] S2.3 In the multi-dimensional comprehensive evaluation framework, the evaluation indicators under each evaluation dimension are managed hierarchically, and a hierarchical indicator structure is output.

[0041] Furthermore, the framework sets "mine development feasibility" as its top-level objective, using this objective as the root node. The four assessment dimensions are then designated as independent second-level nodes. The ore recovery rate and unit product energy consumption under the resource conservation dimension, the wastewater discharge compliance rate and dust emission concentration under the environmental friendliness dimension, the vegetation restoration area ratio and biodiversity index under the ecological harmony dimension, and the local employment ratio and community infrastructure sharing rate under the mine-land collaboration dimension are respectively categorized under their respective assessment dimensions as third-level nodes. Through this top-down node proliferation method, a three-tiered hierarchical relationship of "objective layer—dimensional layer—indicator layer" is ultimately constructed. This hierarchical relationship is then saved in a structured format (such as nested lists or tree dictionaries), outputting a hierarchical indicator structure.

[0042] It should be noted that the hierarchical indicator structure classifies the evaluation indicators within the multi-dimensional comprehensive evaluation framework. Its top level is the implicit "mine development feasibility". The output hierarchical indicator structure only reflects the subordinate relationship of the indicators and does not serve numerical calculation. It is only used for organizational management.

[0043] S2.4 Integrating hierarchical indicator structures, standardized weighted evaluation indicators, and preliminary weights, a multi-dimensional comprehensive evaluation system is constructed.

[0044] Furthermore, the three-layer relationship (mine development feasibility - four assessment dimensions - each assessment indicator) defined in the hierarchical indicator structure is used as the organizational framework. The standardized value and preliminary weight of each assessment indicator in the standardized weighted assessment indicators are embedded into the third-layer node of the organizational framework. The preliminary weights are associated with the same node according to the assessment indicators, ensuring that each assessment indicator contains both the standardized weighted assessment indicator value and the preliminary weight in the organizational framework. Finally, the organizational framework, standardized weighted assessment indicators, and preliminary weights are aligned and bound by the assessment indicator names to form a unified data structure and output a multi-dimensional comprehensive evaluation system.

[0045] S3. Obtain indicators for each dimension from a multi-dimensional comprehensive evaluation system, structure complex problems by combining the analytic hierarchy process, and handle the fuzziness and uncertainty in the evaluation process by combining the fuzzy comprehensive evaluation method to establish a hierarchical evaluation model.

[0046] It should be noted that existing methods usually use the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation methods independently, or only evaluate a single dimension (such as environment or economy) in application. Although some studies have attempted to combine the two, they have not built a complete multi-dimensional indicator system based on a unified data preprocessing process (such as denoising, standardization, and indicator weighting). Moreover, in setting fuzzy linguistic variables and calculating membership degrees, they often rely on subjective experience to define intervals, lacking a direct correlation with the distribution of the original data, resulting in weak repeatability of evaluation results and insufficient synergy between dimensions.

[0047] This invention directly extracts standardized, weighted dimensional indicators with clear hierarchical relationships from a multi-dimensional comprehensive evaluation system, avoiding redundant definition or structural misalignment of indicators. Secondly, it utilizes the analytic hierarchy process (AHP) to construct a hierarchical structured indicator system that conforms to mathematical norms, ensuring that weight calculations strictly correspond to the evaluation objectives and hierarchical logic. Then, the actual values ​​of each indicator are transformed into membership values ​​using a data-driven triangular membership function, and combined with objective weights for fuzzy synthesis. This allows for the simultaneous handling of the structural integrity of indicators, the rationality of weights, and the fuzziness of information within a unified framework. The hierarchical evaluation model reflects the coordinated state of resources, environment, ecology, and society, improving the objectivity, systematicity, and adaptability to uncertain information in mine development evaluation results.

[0048] S3.1 Extract the evaluation indicators under each evaluation dimension from the multi-dimensional comprehensive evaluation system, and number and classify the evaluation indicators according to the dimensions, and output the set of classified evaluation indicators.

[0049] Furthermore, the system iterates through all evaluation indicators contained in the four evaluation dimensions of the multi-dimensional comprehensive evaluation system; assigns a unique dimension number to each evaluation dimension (e.g., resource conservation is D1, environmental friendliness is D2, ecological harmony is D3, and mining-land synergy is D4); assigns consecutive indicator numbers to the evaluation indicators under each evaluation dimension in the order of appearance or alphabetical order, and marks the dimension number to which they belong; organizes all evaluation indicators and their corresponding dimension numbers and indicator numbers into a structured list, and outputs a set of categorized evaluation indicators.

[0050] S3.2 Based on the set of classification evaluation indicators, the hierarchical analysis method is used to construct a hierarchical structured indicator system, with the set of classification evaluation indicators as the top level, the evaluation dimensions as the second level, and the evaluation indicators as the third level.

[0051] Furthermore, the entire set of classification and evaluation indicators is regarded as the target layer of the analytic hierarchy process (AHP), i.e., the top layer; the four numbered evaluation dimensions in the set of classification and evaluation indicators are regarded as the criteria layer, i.e. the second layer; and the numbered evaluation indicators under each evaluation dimension (such as ore recovery rate and unit product energy consumption) are regarded as the scheme layer, i.e. the third layer. Based on the hierarchical relationship recorded in the set of classification and evaluation indicators, a complete hierarchical structure from the top layer to the second layer and then to the third layer is established. The hierarchical relationship between each layer is clarified in the form of a tree diagram or hierarchical matrix, and a hierarchical structured indicator system is output.

[0052] It should be noted that the hierarchical structured indicator system uses the set of classification evaluation indicators as the explicit top layer, and strictly follows the modeling specifications of the analytic hierarchy process to construct a three-level hierarchical structure. The output hierarchical structured indicator system is directly used for subsequent judgment matrix construction and weight calculation, and has a clear decision analysis function.

[0053] S3.3. Based on the hierarchical structured indicator system, automatically calculate the weight values ​​of each evaluation dimension and evaluation indicator, and convert the specific numerical data of each evaluation indicator into fuzzy linguistic variables, and calculate the membership value of each evaluation indicator according to the membership function.

[0054] Furthermore, based on the three-layer structure defined in the hierarchical structured index system, a judgment matrix is ​​constructed by comparing the four evaluation dimensions of the second layer pairwise. A sub-judgment matrix is ​​constructed by comparing the evaluation indicators under each evaluation dimension in the third layer pairwise within their respective dimensions. The analytic hierarchy process is used to calculate the eigenvector corresponding to the largest eigenvalue of the judgment matrix and normalize it to obtain the weight values ​​of each evaluation dimension relative to the top layer and the weight values ​​of each evaluation indicator relative to its respective evaluation dimension. The membership function maps the specific numerical data of each evaluation indicator in the mining development dataset to a preset set of fuzzy linguistic variables (e.g., "low, medium and high" or "poor, average, good and excellent"). The membership function is a triangular or trapezoidal piecewise function, and its parameters are determined by the historical value range of the corresponding evaluation indicator in the mining development dataset. The specific value of each evaluation indicator is substituted into its corresponding membership function, and its membership value to each fuzzy linguistic variable is calculated. The membership value of each evaluation indicator is then output. The membership degree of each fuzzy linguistic variable is calculated using the following expression: ; In the formula, It is the first Each evaluation indicator has an input value of At the time of the first The membership degree of a fuzzy linguistic variable, with a range of [0,1], is dimensionless; It is the first in the mining development data center The specific values ​​of each evaluation indicator are consistent with the physical units of the original indicator (e.g., tons / day, milligrams / liter, or percentage). It is the first of the membership functions of a triangle. The left endpoint of the support interval corresponding to each fuzzy linguistic variable (i.e., the initial value at which the membership degree of the fuzzy linguistic variable increases from 0), and... They have the same dimensions; It is the first of the membership functions of a triangle. The peak points (i.e., positions with a membership degree of 1) corresponding to each fuzzy linguistic variable, and... They have the same dimensions; It is the first of the membership functions of a triangle. The right endpoint of the support interval corresponding to each fuzzy linguistic variable, and They have the same dimensions; It is an index of evaluation indicators; It is an index of fuzzy linguistic variables; It should be noted that the fuzzy linguistic variable set divides the historical value range of each evaluation indicator in the mining development dataset into several continuous semantic intervals that cover the entire domain by analyzing the historical value range of each evaluation indicator. Each semantic interval corresponds to a fuzzy linguistic variable (e.g., "low, medium and high" or "poor, average, good and excellent"). The boundaries of the intervals are determined based on the quantile or equal interval principle of the distribution of evaluation indicator values.

[0055] S3.4 Combining membership values ​​and weight values, the fuzzy comprehensive evaluation results of each evaluation dimension are derived through fuzzy operations to obtain the hierarchical evaluation model.

[0056] Furthermore, the membership values ​​of each evaluation indicator are grouped according to their respective evaluation dimensions, forming a membership matrix with four evaluation dimensions as units. Each row corresponds to an evaluation indicator, and each column corresponds to a fuzzy linguistic variable. This membership matrix is ​​then matched with the weight vectors calculated by the analytic hierarchy process (AHP) for the same evaluation dimension. A weighted fuzzy synthesis operation is performed on the membership vectors and weight vectors for each evaluation dimension to obtain the comprehensive membership degree of that evaluation dimension on each fuzzy linguistic variable. Subsequently, the comprehensive membership vector is normalized to meet the normative requirements of fuzzy sets, and it is then mapped one-to-one with preset evaluation levels (such as "poor, average, good, and excellent") to form an interpretable hierarchical evaluation model.

[0057] S4. Input the indicators of each dimension into the hierarchical evaluation model for structured decomposition and fuzzy reasoning, output the feasibility score of mine development, and classify the preliminary development feasibility level.

[0058] S4.1 Input the evaluation indicators and corresponding weight values ​​of each evaluation dimension into the hierarchical evaluation model, classify, sort and hierarchically decompose each evaluation indicator, and output dimensional structure data.

[0059] Furthermore, the evaluation indicators and their corresponding weight values ​​for each evaluation dimension are input into the hierarchical evaluation model. The evaluation indicators are classified according to the four evaluation dimensions, and their corresponding weight values ​​are retained. Then, within each evaluation dimension, the evaluation indicators are sorted in descending order according to their weight values. The classification results and sorting order are aligned with the three-level membership relationship in the hierarchical structured indicator system (the top level is the set of classification evaluation indicators, the second level is the evaluation dimension, and the third level is the evaluation indicator), and the dimensional structure data is output.

[0060] S4.2 Based on the dimensional structure data and the membership value of each evaluation indicator, a fuzzy inference algorithm is used to perform a fuzzy comprehensive evaluation of each evaluation dimension, and the comprehensive fuzzy score of each evaluation dimension is calculated.

[0061] Furthermore, based on the dimensional structure data and the membership values ​​of each evaluation indicator, for each evaluation dimension, the weighted average synthesis operator in fuzzy comprehensive evaluation is used to perform fuzzy synthesis of the membership values ​​of all evaluation indicators under that evaluation dimension and their weight values, so as to obtain the comprehensive membership vector of that evaluation dimension on each fuzzy linguistic variable. The defuzzification method (such as the centroid method) is applied to the comprehensive membership vector to calculate the comprehensive fuzzy score of each evaluation dimension. The comprehensive fuzzy score for each evaluation dimension is calculated using the following expression: ; In the formula, It is the first The comprehensive fuzzy score of each evaluation dimension (i.e., one of resource conservation, environmental friendliness, ecological harmony or mine-land synergy) is a dimensionless numerical evaluation result used to characterize the overall quality of that evaluation dimension. It is the first The preset quantitative representative values ​​corresponding to each fuzzy linguistic variable (e.g., 1 for "poor", 2 for "average", 3 for "good" and 4 for "excellent") are ordered real numbers and are dimensionless. It is the first The evaluation dimension for the first The comprehensive membership value of each fuzzy linguistic variable is obtained by the synthesis operation in the fuzzy comprehensive evaluation. The value range is [0,1] and is dimensionless. It is an index of fuzzy linguistic variables; It is the total number of fuzzy linguistic variables; It is an index for the evaluation dimension.

[0062] S4.3. Calculate the mine development feasibility score by combining all comprehensive fuzzy scores with dimension weights and performing a weighted average.

[0063] Furthermore, using the comprehensive fuzzy score of each evaluation dimension as the basic value, the scores are fused according to the importance ratio represented by the corresponding dimension weight values, and finally aggregated to generate a mining development feasibility score that represents the overall level.

[0064] S4.4. Set up feasibility score intervals based on the distribution of mine development feasibility scores, compare the mine development feasibility scores with the feasibility score intervals, and determine the preliminary development feasibility level based on the interval to which the mine development feasibility score belongs.

[0065] Furthermore, based on the overall distribution characteristics of the mine development feasibility score in the mine development dataset, several continuous and non-overlapping feasibility score intervals are set, with each feasibility score interval corresponding to a clear preliminary development feasibility level. The mine development feasibility score is matched with all feasibility score intervals to determine the unique feasibility score interval into which the mine development feasibility score falls, and the preliminary development feasibility level corresponding to this feasibility score interval is taken as the output result.

[0066] It should be noted that the feasibility score interval is determined by sorting the feasibility scores of all mine developments and using the natural breakpoint method to divide the range into several continuous intervals that cover the entire scope. Each interval corresponds to a semantically clear preliminary development feasibility level, such as being divided into three segments: low, medium, and high, or three categories: infeasible, conditionally feasible, and feasible. This ensures that the boundaries of each interval can reflect the inherent clustering characteristics of the score distribution.

[0067] Jenks Natural Breaks is a method for dividing data into intervals based on the distribution characteristics of the data itself. It automatically finds the optimal dividing point by minimizing the variance of data within the same interval and maximizing the variance between different intervals.

[0068] S5. Based on the feasibility score and preliminary feasibility level of mine development, the environmental, economic and social benefits of mine development activities are quantified using the full life cycle assessment method, and the comprehensive benefit quantification results are output.

[0069] S5.1. Based on the feasibility score and preliminary feasibility level of the mine development, determine the life cycle stages of the mine development and assign corresponding stage weight values ​​to each life cycle stage.

[0070] Furthermore, based on the mine development feasibility score and the corresponding preliminary development feasibility level, the life cycle stages of mine development (such as exploration stage, construction stage, production stage, or closure stage) are mapped and determined; all categories of preliminary development feasibility levels are clarified (such as "infeasible", "conditionally feasible", and "feasible"); then, according to the logical progress of mine development, "infeasible" is mapped to the exploration stage or closure stage, "conditionally feasible" to the construction stage, and "feasible" to the production stage; the above one-to-one mapping relationship is solidified in tabular form, establishing a correspondence table between preliminary development feasibility levels and mine development life cycle stages; based on the correspondence table, a preset stage weight value is assigned to each mine development life cycle stage, which reflects the relative importance of that stage in the overall development process.

[0071] It should be noted that the stage weight values ​​are determined based on the intensity of resource input, the sustainability of environmental impact, and the criticality of decision-making at each stage of the mining development process. For example, the production stage is given a higher weight due to its long operating cycle and comprehensive impact, while the exploration or closure stage is given a lower weight.

[0072] S5.2. Based on the various life cycle stages of mining development activities, define quantitative indicators for the environmental, economic, and social benefits of each life cycle stage, and obtain the corresponding benefit indicators.

[0073] Furthermore, based on the preliminary feasibility level, the life cycle stages of mine development are determined through a mapping table, including the exploration stage, construction stage, production stage, and closure stage. Quantifiable environmental benefit indicators (such as wastewater reuse rate and ecological disturbance area), economic benefit indicators (such as profit per unit ore and investment payback period), and social benefit indicators (such as local employment ratio and community infrastructure sharing rate) are defined for each stage according to the activity characteristics of each stage of the mine development life cycle. The actual values ​​of these benefit indicators corresponding to each mine development life cycle stage are extracted from the mine development dataset to ensure that each benefit indicator strictly matches its corresponding life cycle stage, ultimately forming a set of environmental benefit indicators, a set of economic benefit indicators, and a set of social benefit indicators organized according to the mine development life cycle stages.

[0074] It should be noted that the activity characteristics of each stage of the mining development life cycle are as follows: the exploration stage is mainly geological survey and resource verification; the construction stage is mainly infrastructure construction and equipment installation; the production stage is mainly ore mining and processing operations; and the closure stage is mainly site remediation and ecological restoration.

[0075] S5.3. Combine the stage weights and benefit indicators of each life cycle stage to calculate the environmental, economic and social benefit scores for each life cycle stage.

[0076] Furthermore, the environmental, economic, and social benefit quantitative indicators corresponding to each stage of the mine development life cycle are obtained from the mine development dataset. Then, each type of benefit indicator is standardized to eliminate dimensional differences. Based on the number of indicators, a single representative value is obtained by arithmetic averaging. The environmental benefit score is formed by aggregating the normalized values ​​of all environmental benefit quantitative indicators in that stage, the economic benefit score is formed by aggregating the normalized values ​​of all economic benefit quantitative indicators in that stage, and the social benefit score is formed by aggregating the normalized values ​​of all social benefit quantitative indicators in that stage.

[0077] S5.4 Integrate the environmental, economic and social benefit scores of each life cycle stage into a comprehensive quantitative result of the benefits of mine development.

[0078] Furthermore, the environmental benefit score, economic benefit score, and social benefit score of each stage of the mine development life cycle are equally weighted and integrated to form the stage comprehensive benefit score. The stage comprehensive benefit scores of all stages of the mine development life cycle are weighted and integrated with their corresponding stage weight values ​​to output the quantitative result of the comprehensive benefit of the mine development.

[0079] S6. The comprehensive benefit quantification results are divided into multiple dimensions and levels to obtain the feasibility level of mine development.

[0080] S6.1. Based on each comprehensive benefit quantification result, set multi-dimensional benefit classification standards, define different benefit intervals for each comprehensive benefit quantification result, divide the intervals according to the multi-dimensional benefit classification standards, and obtain multiple levels of results.

[0081] Furthermore, based on the distribution characteristics of the comprehensive benefit quantification results of all samples in the mining development dataset, the value range is divided into several continuous and non-overlapping benefit intervals using the equal frequency quantile method. According to the order of benefit intervals, the lowest interval is labeled "low benefit," the middle interval is labeled "medium benefit," and the highest interval is labeled "high benefit." If divided into four intervals, they can be labeled "extremely low benefit," "low benefit," "high benefit," and "extremely high benefit," respectively. The naming of semantic labels must reflect the progressive relationship of benefit levels and strictly correspond to the actual distribution range of the comprehensive benefit quantification results of mining development, ensuring that the multi-dimensional benefit classification standard has clear interpretability and consistency, thus forming a multi-dimensional benefit classification standard. Each comprehensive benefit quantification result of mining development is matched with the benefit interval in the multi-dimensional benefit classification standard to determine its corresponding benefit interval, and the corresponding hierarchical results are output.

[0082] S6.2. Based on the hierarchical results of each benefit dimension, define environmental benefits as the primary dimension, economic benefits as the secondary dimension, and social benefits as the third priority dimension, and obtain the priority order.

[0083] Furthermore, the environmental benefit level result corresponding to the comprehensive benefit quantification result of mine development is placed in the highest priority position for decision-making. When the environmental benefit level results of multiple schemes are the same, their economic benefit level results are then compared. If the economic benefit level results are still the same, the social benefit level results are then compared, thus forming a priority order composed of environmental benefit level results, economic benefit level results and social benefit level results.

[0084] S6.3. Merge multiple results at different levels according to priority and using the hierarchical merging rules to obtain the feasibility level of mine development.

[0085] Furthermore, the initial level is determined primarily based on the environmental benefit level results. If multiple schemes have the same environmental benefit level results, they are further subdivided based on the economic benefit level results. If the economic benefit level results are still the same, they are further differentiated based on the social benefit level results, resulting in a unique mine development feasibility level.

[0086] This embodiment also provides a computer device applicable to the assessment method for the feasibility level of green mine development, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the assessment method for the feasibility level of green mine development as proposed in the above embodiment.

[0087] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0088] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the assessment method for determining the feasibility level of green mine development as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0089] In summary, this invention, starting from four dimensions—resource conservation, environmental friendliness, ecological harmony, and mine-land synergy—defines and classifies relevant assessment indicators to construct a multi-dimensional comprehensive evaluation system. This ensures that all aspects of the impact of mining development are fully considered, promoting green and sustainable development. Furthermore, by using the analytic hierarchy process (AHP) to structure the assessment indicators and combining it with fuzzy comprehensive evaluation methods to handle uncertainties, the accuracy and adaptability of the assessment results are improved, providing strong support for scientific decision-making in mining development. This makes the feasibility assessment of mining development more comprehensive and accurate, ensuring that all key factors are effectively considered.

[0090] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for assessing the feasibility level of green mine development, characterized in that: include, Collect multi-dimensional assessment data on mine development and obtain a mine development dataset through data cleaning, noise reduction, and standardization; Based on the mining development dataset, the evaluation indicators are preliminarily defined and classified from four dimensions: resource conservation, environmental friendliness, ecological harmony, and mine-land synergy, and a multi-dimensional comprehensive evaluation system is constructed. The multi-dimensional comprehensive evaluation system obtains indicators for each dimension, combines the analytic hierarchy process to structure complex problems, and combines the fuzzy comprehensive evaluation method to deal with the fuzziness and uncertainty in the evaluation process, and establishes a hierarchical evaluation model. The indicators of each dimension are input into the hierarchical evaluation model for structured decomposition and fuzzy reasoning, outputting the feasibility score of mine development and classifying the preliminary development feasibility level. Based on the feasibility score and preliminary feasibility level of mine development, the environmental, economic and social benefits of mine development activities are quantified using the full life cycle assessment method, and the comprehensive benefit quantification results are output. The comprehensive benefit quantification results are divided into multiple dimensions and levels to obtain the feasibility level of mine development.

2. The method for assessing the feasibility level of green mine development as described in claim 1, characterized in that: The specific steps for obtaining the mine development dataset are as follows. The system examines multi-dimensional assessment data of mine development, identifies missing and outlier values, fills in missing values ​​and corrects outliers, and outputs a cleaned dataset. Identify abnormal fluctuations in the cleaned data, remove noise through smoothing and correct the abnormal fluctuations, and output the denoised dataset. Adjust the scale of the denoised dataset, compare all numerical data within the same range, process categorical data into numerical data, and output the mining development dataset.

3. The method for assessing the feasibility level of green mine development as described in claim 2, characterized in that: Based on the mining development dataset, the evaluation indicators are initially defined and classified from four dimensions: resource conservation, environmental friendliness, ecological harmony, and mine-land synergy. A multi-dimensional comprehensive evaluation system is then constructed, with the specific steps as follows: Statistical analysis and data mining are performed on mining data, environmental monitoring data, resource utilization data and social impact data in the mining development dataset. The analysis focuses on resource consumption, environmental impact, ecological restoration and social collaboration involved in the mining process. Four evaluation dimensions are defined and corresponding evaluation indicators are selected for each evaluation dimension. A multi-dimensional comprehensive evaluation framework is constructed based on four evaluation dimensions. The evaluation indicators of each evaluation dimension are standardized, and preliminary weights are assigned to each evaluation indicator to obtain standardized weighted evaluation indicators. In the multi-dimensional comprehensive evaluation framework, the evaluation indicators under each evaluation dimension are managed hierarchically, and a hierarchical indicator structure is output. By integrating hierarchical indicator structures, standardized weighted evaluation indicators, and preliminary weights, a multi-dimensional comprehensive evaluation system is constructed.

4. The method for assessing the feasibility level of green mine development as described in claim 3, characterized in that: The process involves obtaining indicators from various dimensions of a multi-dimensional comprehensive evaluation system, structuring complex problems using the analytic hierarchy process (AHP), and addressing fuzzy and uncertainties in the evaluation process using fuzzy comprehensive evaluation methods to establish a hierarchical evaluation model. The specific steps are as follows: The evaluation indicators for each evaluation dimension are extracted from the multi-dimensional comprehensive evaluation system, and the evaluation indicators are numbered and classified according to the dimension, and a set of classified evaluation indicators is output. Based on the set of classification and evaluation indicators, the hierarchical analysis method is used to construct a hierarchical structured indicator system, with the set of classification and evaluation indicators as the top level, the evaluation dimensions as the second level, and the evaluation indicators as the third level. The weight values ​​of each evaluation dimension and evaluation indicator are automatically calculated based on the hierarchical structured indicator system. The specific numerical data of each evaluation indicator are converted into fuzzy linguistic variables, and the membership value of each evaluation indicator is calculated according to the membership function. By combining membership values ​​and weight values, fuzzy comprehensive evaluation results for each evaluation dimension are derived through fuzzy computation, thus obtaining a hierarchical evaluation model.

5. The method for assessing the feasibility level of green mine development as described in claim 4, characterized in that: The process involves inputting various dimensional indicators into a hierarchical evaluation model for structured decomposition and fuzzy reasoning, outputting a mine development feasibility score. The specific steps are as follows: The evaluation indicators and corresponding weight values ​​of each evaluation dimension are input into the hierarchical evaluation model. Each evaluation indicator is classified, sorted, and hierarchically decomposed to output dimensional structure data. Based on the dimensional structure data and the membership value of each evaluation indicator, a fuzzy inference algorithm is used to perform a fuzzy comprehensive evaluation of each evaluation dimension and calculate the comprehensive fuzzy score of each evaluation dimension. The feasibility score for mine development is calculated by weighting all the comprehensive fuzzy scores together with the dimensional weights.

6. The method for assessing the feasibility level of green mine development as described in claim 1, characterized in that: The preliminary development feasibility level is determined by setting a feasibility score range based on the distribution of mine development feasibility scores, comparing the mine development feasibility score with the feasibility score range, and determining the range to which the mine development feasibility score belongs.

7. The method for assessing the feasibility level of green mine development as described in claim 6, characterized in that: Based on the mine development feasibility score and preliminary development feasibility level, the environmental, economic, and social benefits of mine development activities are quantified using a full life cycle assessment method, outputting a comprehensive benefit quantification result. The specific steps are as follows. Based on the mine development feasibility score and preliminary development feasibility level, the life cycle stages of mine development are determined, and corresponding stage weight values ​​are assigned to each life cycle stage. Based on the various life cycle stages of mining development activities, define quantitative indicators for the environmental, economic, and social benefits of each life cycle stage, and obtain the corresponding benefit indicators. By combining the stage weights and benefit indicators of each life cycle stage, the environmental, economic, and social benefit scores for each life cycle stage are calculated; the environmental, economic, and social benefit scores of each life cycle stage are then integrated into a comprehensive quantitative result of the benefits of mine development.

8. The method for assessing the feasibility level of green mine development as described in claim 7, characterized in that: The process of quantifying comprehensive benefits and classifying them into multi-dimensional hierarchical levels to obtain the feasibility level of mine development involves the following specific steps. Based on each comprehensive benefit quantification result, a multi-dimensional benefit classification standard is set, and a different benefit range is defined for each comprehensive benefit quantification result. The range is divided according to the multi-dimensional benefit classification standard to obtain multiple levels of results. Based on the hierarchical results of each benefit dimension, environmental benefits are defined as the primary dimension, economic benefits as the secondary dimension, and social benefits as the third priority dimension, and the priority order is obtained. The results from multiple levels are merged according to priority and hierarchical merging rules to obtain the feasibility level of mine development.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for assessing the feasibility level of green mine development as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for assessing the feasibility level of green mine development as described in any one of claims 1 to 8.

Images